© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 14518
    Prev
    Next
    INDEX
    Explanations

    phrases related to criminal organizations or violent activities

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    585
    +0.17
    0.6%
    276
    +0.13
    0.5%
    453
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.17
    0.10
    326
    +0.13
    0.08
    585
    +0.13
    0.06
    Negative Logits
    OPLE
    -1.00
    éĸ
    -0.97
     Parenthood
    -0.95
    /+
    -0.94
    aeda
    -0.92
     Dame
    -0.89
     Clause
    -0.87
     Springs
    -0.86
    etsk
    -0.82
    ippi
    -0.82
    POSITIVE LOGITS
    ster
    1.41
    sta
    1.39
    sters
    1.35
    busters
    1.30
    bang
    1.28
    ãĥ£
    1.20
    oly
    1.13
    regate
    1.08
    lins
    1.01
    bing
    1.01
    Activations Density 1.275%

    No Known Activations